arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.12431cs.CVcs.AI
收藏

深度学习框架中的几何约束:综述

Geometric Constraints in Deep Learning Frameworks: A Survey

Indiana University Bloomington(印第安纳大学布卢明顿分校)

Vibhas K Vats, David J Crandall

AI总结:

本综述系统梳理了深度学习框架中的几何约束方法,提出新分类法,并比较其在深度估计等视觉任务中的应用,展望未来研究方向。

摘要:

立体摄影测量是一种成熟的场景理解技术。其起源至少可追溯到19世纪,当时人们开始研究利用照片来测量世界的物理属性。此后,人们探索了数千种方法。经典的“从立体图像恢复形状”几何技术,其基础是利用几何来定义场景和相机的约束,而深度学习则在不显式建模几何的情况下进行。在本综述中,我们探讨了受几何启发的基于深度学习的框架。我们比较并对比了集成到深度学习框架中用于深度估计及其他密切相关视觉任务的几何强制约束。我们为现代深度学习框架中常用的几何强制约束提出了一种新的分类法。我们还提出了富有洞察力的观察结果和潜在的未来研究方向。

英文摘要:

Stereophotogrammetry is an established technique for scene understanding. Its origins go back to at least the 1800s when people first started to investigate using photographs to measure the physical properties of the world. Since then, thousands of approaches have been explored. The classic geometric technique of Shape from Stereo is built on using geometry to define constraints on scene and camera deep learning without any attempt to explicitly model the geometry. In this survey, we explore geometry-inspired deep learning-based frameworks. We compare and contrast geometry enforcing constraints integrated into deep learning frameworks for depth estimation and other closely related vision tasks. We present a new taxonomy for prevalent geometry enforcing constraints used in modern deep learning frameworks. We also present insightful observations and potential future research directions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑